运行 run_squad.py 以微调 Google BERT 模型（官方 tensorflow 预训练模型）时无法加载（恢复）TensorFlow 检查点

Question

I am new to deep learning and NLP, and now trying to get started with the pre-trained Google BERT model. Since I intended to build a QA system with BERT, I decided to start from the SQuAD related fine-tuning.

I followed the instructions from README.md in the official Google BERT GitHub repository .

I typed the code as following:

export BERT_BASE_DIR=/home/bert/Dev/venv/uncased_L-12_H-768_A-12/
export SQUAD_DIR=/home/bert/Dev/venv/squad
python run_squad.py \
  --vocab_file=$BERT_BASE_DIR/vocab.txt \
  --bert_config_file=$BERT_BASE_DIR/bert_config.json \
  --init_checkpoint=$BERT_BASE_DIR/bert_model.ckpt \
  --do_train=True \
  --train_file=$SQUAD_DIR/train-v1.1.json \
  --do_predict=True \
  --predict_file=$SQUAD_DIR/dev-v1.1.json \
  --train_batch_size=12 \
  --learning_rate=3e-5 \
  --num_train_epochs=2.0 \
  --max_seq_length=384 \
  --doc_stride=128 \
  --output_dir=/tmp/squad_base/

and after minutes(when the training started), I got this:

a lot of output omitted
INFO:tensorflow:start_position: 53
INFO:tensorflow:end_position: 54
INFO:tensorflow:answer: february 1848
INFO:tensorflow:***** Running training *****
INFO:tensorflow:  Num orig examples = 87599
INFO:tensorflow:  Num split examples = 88641
INFO:tensorflow:  Batch size = 12
INFO:tensorflow:  Num steps = 14599
INFO:tensorflow:Calling model_fn.
INFO:tensorflow:Running train on CPU
INFO:tensorflow:*** Features ***
INFO:tensorflow:  name = end_positions, shape = (12,)
INFO:tensorflow:  name = input_ids, shape = (12, 384)
INFO:tensorflow:  name = input_mask, shape = (12, 384)
INFO:tensorflow:  name = segment_ids, shape = (12, 384)
INFO:tensorflow:  name = start_positions, shape = (12,)
INFO:tensorflow:  name = unique_ids, shape = (12,)
INFO:tensorflow:Error recorded from training_loop: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for /home/bert/Dev/venv/uncased_L-12_H-768_A-12//bert_model.ckpt
INFO:tensorflow:training_loop marked as finished
WARNING:tensorflow:Reraising captured error
Traceback (most recent call last):
  File "run_squad.py", line 1283, in <module>
    tf.app.run()
  File "/home/bert/Dev/venv/lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 125, in run
    _sys.exit(main(argv))
  File "run_squad.py", line 1215, in main
    estimator.train(input_fn=train_input_fn, max_steps=num_train_steps)
  File "/home/bert/Dev/venv/lib/python3.5/site-packages/tensorflow/contrib/tpu/python/tpu/tpu_estimator.py", line 2400, in train
    rendezvous.raise_errors()
  File "/home/bert/Dev/venv/lib/python3.5/site-packages/tensorflow/contrib/tpu/python/tpu/error_handling.py", line 128, in raise_errors
    six.reraise(typ, value, traceback)
  File "/home/bert/Dev/venv/lib/python3.5/site-packages/six.py", line 693, in reraise
    raise value
  File "/home/bert/Dev/venv/lib/python3.5/site-packages/tensorflow/contrib/tpu/python/tpu/tpu_estimator.py", line 2394, in train
    saving_listeners=saving_listeners
  File "/home/bert/Dev/venv/lib/python3.5/site-packages/tensorflow/python/estimator/estimator.py", line 356, in train
    loss = self._train_model(input_fn, hooks, saving_listeners)
  File "/home/bert/Dev/venv/lib/python3.5/site-packages/tensorflow/python/estimator/estimator.py", line 1181, in _train_model
    return self._train_model_default(input_fn, hooks, saving_listeners)
  File "/home/bert/Dev/venv/lib/python3.5/site-packages/tensorflow/python/estimator/estimator.py", line 1211, in _train_model_default
    features, labels, model_fn_lib.ModeKeys.TRAIN, self.config)
  File "/home/bert/Dev/venv/lib/python3.5/site-packages/tensorflow/contrib/tpu/python/tpu/tpu_estimator.py", line 2186, in _call_model_fn
    features, labels, mode, config)
  File "/home/bert/Dev/venv/lib/python3.5/site-packages/tensorflow/python/estimator/estimator.py", line 1169, in _call_model_fn
    model_fn_results = self._model_fn(features=features, **kwargs)
  File "/home/bert/Dev/venv/lib/python3.5/site-packages/tensorflow/contrib/tpu/python/tpu/tpu_estimator.py", line 2470, in _model_fn
    features, labels, is_export_mode=is_export_mode)
  File "/home/bert/Dev/venv/lib/python3.5/site-packages/tensorflow/contrib/tpu/python/tpu/tpu_estimator.py", line 1250, in call_without_tpu
    return self._call_model_fn(features, labels, is_export_mode=is_export_mode)
  File "/home/bert/Dev/venv/lib/python3.5/site-packages/tensorflow/contrib/tpu/python/tpu/tpu_estimator.py", line 1524, in _call_model_fn
    estimator_spec = self._model_fn(features=features, **kwargs)
  File "run_squad.py", line 623, in model_fn
    ) = modeling.get_assignment_map_from_checkpoint(tvars, init_checkpoint)
  File "/home/bert/Dev/venv/bert/modeling.py", line 330, in get_assignment_map_from_checkpoint
    init_vars = tf.train.list_variables(init_checkpoint)
  File "/home/bert/Dev/venv/lib/python3.5/site-packages/tensorflow/python/training/checkpoint_utils.py", line 95, in list_variables
    reader = load_checkpoint(ckpt_dir_or_file)
  File "/home/bert/Dev/venv/lib/python3.5/site-packages/tensorflow/python/training/checkpoint_utils.py", line 64, in load_checkpoint
    return pywrap_tensorflow.NewCheckpointReader(filename)
  File "/home/bert/Dev/venv/lib/python3.5/site-packages/tensorflow/python/pywrap_tensorflow_internal.py", line 314, in NewCheckpointReader
    return CheckpointReader(compat.as_bytes(filepattern), status)
  File "/home/bert/Dev/venv/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py", line 526, in __exit__
    c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.NotFoundError: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for /home/bert/Dev/venv/uncased_L-12_H-768_A-12//bert_model.ckpt

It seems that tensorflow failed to find the checkpoint file, but as far as i know about it, a tensorflow checkpoint "file" is actually three files, and this is correct way to call it(with the path and prefix).

I am placing files in the right place, I believe:

(venv) bert@bert-System-Product-Name:~/Dev/venv/uncased_L-12_H-768_A-12$ pwd
/home/bert/Dev/venv/uncased_L-12_H-768_A-12
(venv) bert@bert-System-Product-Name:~/Dev/venv/uncased_L-12_H-768_A-12$ ls
bert_config.json  bert_model.ckpt.data-00000-of-00001  bert_model.ckpt.index  bert_model.ckpt.meta  vocab.txt

I am running on Ubuntu 16.04 LTS , with NVIDIA GTX 1080 Ti (CUDA 9.0) , with Anaconda python 3.5 distribution , with tensorflow-gpu 1.11.0 in a virtual environment.

I am expecting the code to run smoothly and start training(fine-tune) since it is official code and I got the files placed as instructions.

Answer 1

I am answering my own question.

I have just solved the problem by simply remove the slash( / ) in the $BERT_BASE_DIR , so the variable changed from '/home/bert/Dev/venv/uncased_L-12_H-768_A-12/' to '/home/bert/Dev/venv/uncased_L-12_H-768_A-12' .

So there is no more double slash in the prefix "/home/bert/Dev/venv/uncased_L-12_H-768_A-12//bert_model.ckpt" .

It seems that single slash or double slash are considered different by checkpoint restore functions in tensorflow since I believe that bash interprets them as identical.